ui-design

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for generating user interface designs in HTML and Tailwind CSS. It follows standard formatting and styling rules without requesting sensitive permissions or accessing external untrusted scripts.
  • [EXTERNAL_DOWNLOADS]: The skill references well-known and trusted external services for UI components, including Lucide icons and Unsplash for placeholder images. These are standard practices for web development prompts.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided design specifications and code snippets as input for design inspiration. While this constitutes a data ingestion surface, it is consistent with the skill's primary purpose and is managed by standard agent safety protocols.
  • Ingestion points: User-supplied design, code, or HTML provided for inspiration (SKILL.md).
  • Boundary markers: None explicitly defined in the prompt.
  • Capability inventory: The skill generates HTML and JavaScript (Chart.js) code.
  • Sanitization: No explicit sanitization logic is provided in the prompt, relying on model-level safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:00 PM
Security Audit — agent-trust-hub — ui-design